Memòria cau
Estratègies i implementació de memòria cau
context-optimization
eyadsibai
Use when optimizing agent context, reducing token costs, implementing KV-cache optimization, or asking about "context optimization", "token reduction", "context limits", "observation masking", "context budgeting", "context partitioning"
architecture-documenter
CuriousLearner
Document system architecture and technical design decisions for effective team communication and ...
nextjs-reviewer
jaredpalmer
Review Next.js App Router code for optimal Partial Prerendering (PPR), caching strategy, Suspense boundaries, and React Query integration. Ensure adherence to Next.js 16+ Cache Components best practices.
SiteGround Cache Buster Skill
CrazySwami
visual-qa - Screenshot testing after changes
flutter-skill
thruthesky
"본 스킬은 Flutter 프레임워크로 앱을 개발하는 데 반드시 따라야 하는 UI/UX 디자인, 상태관리, 네트워킹, API 연동에 관한 가이드라인 제공합니다. 본 스킬은 선택적인 정보를 제공하는 것이 아니라 Flutter 앱 개발에 필수적인 지침을 제공하며 반드시 준수해야 할 사항들을 제공합니다. 개발자가 디자인, UI, UX, 디자인 효과, 상태관리, 라우팅, 네트워킹, API 연동에 관한 요청, 코믹디자인, Comic 관련 요청, 채팅, FCM, 푸시 알림, 메시지, 알림에 관한 요청이 있을 때 반드시 본 스킬을 사용해서 본 스킬이 제공하는 대로 작업을 수행해야 합니다. 각 스킬 문서에의 상단에는 반드시 따라야 할 Workflow 가 있습니다. 반드시 그 Workflow 를 따라야 합니다. 추가 트리거 키워드 - 딥링크, deep link, 캐싱, cache, 아이콘, FontAwesome, Isolate, 동시성, concurrency, 카카오톡, KakaoTalk, Crashlytics, 크래시 리포팅, 공유, share, share_plus, 공유 버튼 (project)"
spring-boot-full-stack
mduongvandinh
Complete Java Spring Boot skill set for building enterprise applications. Includes modular architecture with optional components: - PostgreSQL database with JPA/Hibernate + Flyway migration - Redis caching (optional) - Kafka/RabbitMQ messaging (optional, choose one) - JWT + OAuth2 authentication (optional OAuth2) - RBAC authorization (optional) - TDD with Mockito - Spec-First Development with OpenSpec
laravel-infrastructure
anilcancakir
"Laravel Horizon queues, Octane performance, Reverb WebSockets, Redis caching, PostgreSQL database. ALWAYS activate when: working with queue jobs, cache, sessions, broadcasting, database performance, supervisor, worker. Triggers on: job failed, queue stuck, cache not clearing, Redis connection, broadcast event, WebSocket, real-time, Horizon dashboard, Octane memory leak, slow query, N+1, database timeout, connection refused, kuyruk çalışmıyor, cache temizlenmiyor, job başarısız, worker durdu, broadcast çalışmıyor, real-time gelmiyor."
study-assistant
planetis-m
Study assistant workflow for lecture-slide exam prep using the pdfocr CLI. Use when a task involves reading PDF slides, transcribing slide text, cleaning OCR output, and generating exam-focused deliverables such as study notes, lecture-style explanations, ELI5 explanations, flashcards, Mermaid mind maps, quizzes, essay questions, or one-step PDF-to-notes output.
managing-project-customizations
klamping
Use when initializing or refreshing project-specific WebdriverIO context so other skills can reuse cached configuration, conventions, and environment details with lower token and execution cost.
nextjs-16-architecture
horuz-ai
Comprehensive Next.js v16 development with Cache Components, feature-based architecture, and best practices. Use for ANY Next.js 16 task to know - (1) Project structure with features folder pattern, (2) Where to fetch data with use cache, (3) Server vs Client component decisions, (4) One file per query/type/schema/hook pattern, (5) Cache invalidation with updateTag/revalidateTag, (6) Proper component organization within features. Apply to all Next.js 16 development tasks.
pdf-to-markdown
aliceisjustplaying
Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.
memory-management
richfrem
"Tiered memory system for cognitive continuity across agent sessions. Manages hot cache (session context loaded at boot) and deep storage (loaded on demand). Use when: (1) starting a session and loading context, (2) deciding what to remember vs forget, (3) promoting/demoting knowledge between tiers, (4) user says 'remember this' or asks about project history."
sqldown
mbailey
Bidirectional markdown ↔ SQLite conversion with column limit protection and smart section extraction. Import with Python, query with sqlite3.
conversation-api-cost
xoykor
Estime o custo em dólares de uma conversa como uso da API, usando tokens explícitos ou as mensagens visíveis da conversa; use quando o usuário perguntar quanto a conversa custaria, quiser comparar modelos ou calcular gasto por tokens.
cache-strategy
manastalukdar
Implement caching strategies for HTTP, service workers, and memoization
database-operations
jgarrison929
Use when designing database schemas, writing migrations, optimizing SQL queries, fixing N+1 problems, creating indexes, setting up PostgreSQL, configuring EF Core, implementing caching, partitioning tables, or any database performance question.
find-todos
manastalukdar
Locate development tasks and TODO comments across the codebase
cloud-architect
jgarrison929
Use when designing cloud infrastructure on AWS, Azure, or GCP. Invoke for architecture decisions, cost optimization, networking, high availability, serverless patterns, or multi-cloud strategies.
architecture-diagram
manastalukdar
Generate architecture diagrams in Mermaid, PlantUML, or diagrams.net formats
vercel-react-best-practices
rakaadi
React performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React code to ensure optimal performance patterns. Triggers on tasks involving React components, data fetching, bundle optimization, or performance improvements.
format
manastalukdar
Auto-detect and apply code formatting using project's configured formatter
gcp-batch-inference
viktor-ferenczi
Running batch inference on Google Cloud (also known as Vertex AI)
context-optimization
ken-cavanagh-glean
Apply optimization techniques to extend effective context capacity. Use when context limits constrain agent performance, when optimizing for cost or latency, or when implementing long-running agent systems.
turborepo-caching
EngineerWithAI
Configure Turborepo for efficient monorepo builds with local and remote caching. Use when setting up Turborepo, optimizing build pipelines, or implementing distributed caching.